publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2026

  1. mice_preview.jpg
    Editing Everything Everywhere All at Once
    Fabio Quattrini*, Carmine Zaccagnino*, Enis Simsar, Marta Tintoré Gazulla, Rita Cucchiara, Alessio Tonioni, and Silvia Cascianelli
    In ECCV, 2026
    arXiv PDF Code Website
  2. SeqLoRA: Bilevel Orthogonal Adaptation for Continual Multi-Concept Generation
    Javad Parsa*, Enis Simsar*, Amir Joudaki, Thomas Hofmann, and André M. H. Teixeira
    arXiv preprint arXiv:2605.22743, 2026
    In submission
    arXiv PDF
  3. idattn_preview.jpg
    Shifting the Breaking Point of Flow Matching for Multi-Instance Editing
    Carmine Zaccagnino*, Fabio Quattrini*, Enis Simsar, Marta Tintoré Gazulla, Rita Cucchiara, Alessio Tonioni, and Silvia Cascianelli
    In ICML, 2026
    arXiv PDF Code Website
  4. Provable Forgetting Bounds Drive Capacity Savings: Spectral Thresholding in Continual LoRA
    Louis Barinka, Giulia Lanzillotta, Enis Simsar, Tanguy Dieudonné, and Thomas Hofmann
    In ICML Workshops (CoLoRAI and CATS), 2026
  5. When One Adapter Speaks for Many: Discovering Low-Rank Redundancy in Continual Fine-Tuning
    Tanguy Dieudonné, Giulia Lanzillotta, Enis Simsar, Louis Barinka, and Thomas Hofmann
    In ICML Workshop (CoLoRAI), 2026
  6. refam_preview.jpg
    RefAM: Attention Magnets for Zero-Shot Referral Segmentation
    Anna Kukleva*, Enis Simsar*, Alessio Tonioni, Muhammad Ferjad Naeem, Federico Tombari, Jan Eric Lenssen, and Bernt Schiele
    TMLR, 2026
    arXiv PDF Website
  7. fullflow_preview.jpg
    FullFlow: Upgrading Text-to-Image Flow Matching Models for Bidirectional Vision–Language Generation
    Eric Tillmann Bill, Enis Simsar, Alessio Tonioni, and Thomas Hofmann
    arXiv preprint arXiv:2605.20316, 2026
    arXiv PDF Website
  8. focus_preview.jpg
    FOCUS: Optimal Control for Multi-Entity World Modeling in Text-to-Image Generation
    Eric Tillmann Bill, Enis Simsar, and Thomas Hofmann
    In CVPR — CVEU Workshop, Jun 2026
    CVEU Workshop Oral arXiv HTML PDF Code Website
  9. Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography
    Ibrahim Ethem Hamamci, Sezgin Er, Chenyu Wang, Furkan Almas, Ayse Gulnihan Simsek, Sevval Nil Esirgun, Irem Dogan, Omer Faruk Durugol, Benjamin Hou, Suprosanna Shit, Weicheng Dai, Murong Xu, Hadrien Reynaud, Muhammed Furkan Dasdelen, Bastian Wittmann, Tamaz Amiranashvili, Enis Simsar, and 13 more authors
    Nature Biomedical Engineering, 10, 1610–1628 , 2026
    DOI arXiv HTML PDF

2025

  1. loraclr_preview.jpg
    LoRACLR: Contrastive Adaptation for Customization of Diffusion Models
    Enis Simsar, Thomas Hofmann, Federico Tombari, and Pinar Yanardag
    In CVPR, 2025
    arXiv PDF Code Website
  2. clora_preview.jpg
    CLoRA: Contrastive Test-Time Composition of Multiple LoRA Models for Image Generation
    Tuna Han Salih Meral*, Enis Simsar*, Federico Tombari, and Pinar Yanardag
    In ICCV, 2025
    Highlight arXiv PDF Code Website
  3. uip2p_preview.jpg
    UIP2P: Unsupervised Instruction-based Image Editing via Edit Reversibility Constraint
    Enis Simsar, Alessio Tonioni, Yongqin Xian, Thomas Hofmann, and Federico Tombari
    In ICCV, 2025
    arXiv PDF Website
  4. lime_preview.jpg
    LIME: Localized Image Editing via Attention Regularization in Diffusion Models
    Enis Simsar, Alessio Tonioni, Yongqin Xian, Thomas Hofmann, and Federico Tombari
    In WACV, 2025
    Oral arXiv PDF Code Website
  5. SHYI: Action Support for Contrastive Learning in High-Fidelity Text-to-Image Generation
    Tianxiang Xia, Lin Xiao, Yannick Montorfani, Francesco Pavia, Enis Simsar, and Thomas Hofmann
    arXiv preprint arXiv:2501.09055, 2025
  6. IC-Portrait: In-Context Matching for View-Consistent Personalized Portrait
    Han Yang, Enis Simsar, Sotiris Anagnostidis, Yanlong Zang, Thomas Hofmann, and Ziwei Liu
    arXiv preprint arXiv:2501.17159, 2025
  7. Automating Spinal Alignment Analysis with Machine Learning and PCdare Software: Focus on Idiopathic Scoliosis
    Kübra Stoican, Enis Simsar, Martin Bertsch, Saša Ćuković, and Mirko Kaiser
    In Medical Imaging 2025, 2025
  8. JEDI: The Force of Jensen-Shannon Divergence in Disentangling Diffusion Models
    Eric Tillmann Bill, Enis Simsar, and Thomas Hofmann
    In ICML Workshop on Test-Time Adaptation, 2025
    arXiv Code Website

2024

  1. conform_preview.jpg
    CONFORM: Contrast is All You Need for High-Fidelity Text-to-Image Diffusion Models
    Tuna Han Salih Meral, Enis Simsar, Federico Tombari, and Pinar Yanardag
    In CVPR, 2024
    arXiv PDF Code Website
  2. stylebreeder_preview.jpg
    StyleBreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models
    Matthew Zheng*, Enis Simsar*, Hidir Yesiltepe, Federico Tombari, Joel Simon, and Pinar Yanardag Delul
    NeurIPS Datasets Track, 2024
    PDF Code Dataset Website
  3. Application and Service Context Aware Cell Selection
    Gencer Cili, Rawad Rahme, Mahak Goindani, Nabil Akdim, and Enis Simsar
    Aug 2024
    US Patent App. 18/635,234
  4. PixLens: A Novel Framework for Disentangled Evaluation in Diffusion-Based Image Editing with Object Detection+ SAM
    Stefan Stefanache, Lluı́s Pastor Pérez, Julen Costa Watanabe, Ernesto Sanchez Tejedor, Thomas Hofmann, and Enis Simsar
    arXiv preprint arXiv:2410.05710, 2024
  5. MegaPortrait: Revisiting Diffusion Control for High-fidelity Portrait Generation
    Han Yang, Sotiris Anagnostidis, Enis Simsar, and Thomas Hofmann
    arXiv preprint arXiv:2411.04357, 2024
  6. GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes
    Ibrahim Ethem Hamamci, Sezgin Er, Anjany Sekuboyina, Enis Simsar, Alperen Tezcan, Ayse Gulnihan Simsek, and 10 more authors
    In ECCV, 2024
    DOI arXiv HTML PDF

2023

  1. LatentSwap3D: Semantic Edits on 3D Image GANs
    Enis Simsar, Alessio Tonioni, Evin Pinar Ornek, and Federico Tombari
    In ICCVW, 2023
  2. Fantastic Style Channels and Where to Find Them: A Submodular Framework for Discovering Diverse Directions in GANs
    Enis Simsar, Umut Kocasari, Ezgi Gülperi Er, and Pinar Yanardag
    In WACV, 2023
  3. Diffusion-Based Hierarchical Multi-Label Object Detection to Analyze Panoramic Dental X-rays
    Ibrahim Ethem Hamamci, Sezgin Er, Enis Simsar, Anjany Sekuboyina, Mustafa Gundogar, Bernd Stadlinger, Albert Mehl, and Bjoern Menze
    In MICCAI, 2023
  4. DENTEX: Dental Enumeration and Tooth Pathosis Detection Benchmark for Panoramic X-ray
    Ibrahim Ethem Hamamci, Sezgin Er, Omer Faruk Durugol, Gulsade Rabia Cakmak, Ezequiel de la Rosa, Enis Simsar, and 37 more authors
    arXiv preprint arXiv:2305.19112, 2023
    Revised November 2025
    arXiv PDF Code

2022

  1. Object-Aware Monocular Depth Prediction with Instance Convolutions
    Enis Simsar, Evin Pınar Örnek, Fabian Manhardt, Helisa Dhamo, Nassir Navab, and Federico Tombari
    IEEE Robotics and Automation Letters, 2022
  2. Rank in Style: A Ranking-based Approach to Find Interpretable Directions
    Umut Kocasari, Kerem Zaman, Mert Tiftikci, Enis Simsar, and Pinar Yanardag
    In CVPR Workshops (CVFAD), 2022
    PDF

2021

  1. Graph2Pix: A Graph-Based Image to Image Translation Framework
    Dilara Gokay*, Enis Simsar*, Efehan Atici, Alper Ahmetoglu, Atif Emre Yuksel, and Pinar Yanardag
    In ICCVW, 2021
  2. LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions
    Oğuz Kaan Yüksel*, Enis Simsar*, Ezgi Gülperi Er, and Pinar Yanardag
    In ICCV, 2021
  3. Dental Enumeration and Multiple Treatment Detection on Panoramic X-rays Using Deep Learning
    Atıf Emre Yüksel, Sadullah Gültekin, Enis Simsar, Şerife Damla Özdemir, Mustafa Gündoğar, Salih Barkın Tokgöz, and İbrahim Ethem Hamamcı
    Scientific Reports, 2021
  4. Twitter interaction data of Electra cryptocurrency community’s Twitter handle followers and a code for follower interaction analysis
    Enis Simsar and Koray Caliskan
    Retrieved from GitHub Repository https://github. com/enisimsar/DataMoney https://doi. org/10.5281/zenodo, 2021

2019

  1. Comparison of Deep Generative Models for the Generation of Handwritten Character Images
    Ömer Kırbıyık, Enis Simsar, and A Taylan Cemgil
    In 2019 27th Signal Processing and Communications Applications Conference (SIU), 2019